© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4620
    Prev
    Next
    INDEX
    Explanations

    mentions of "season" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ידי
    -0.42
    oa̍t
    -0.38
     chitar
    -0.38
    wußt
    -0.34
     Hughes
    -0.34
     Hilfs
    -0.34
    grafías
    -0.32
     automatique
    -0.32
    ụp
    -0.31
    тное
    -0.31
    POSITIVE LOGITS
     season
    4.56
     Season
    3.98
    Season
    3.97
    season
    3.95
     SEASON
    3.83
    SEASON
    3.45
     seasons
    3.39
     saison
    3.06
    seasons
    2.97
     Seasons
    2.84
    Activations Density 0.091%

    No Known Activations